Results section (Principles of
preparing figures and tables)
Training Workshop on Scientific Research,
Communication and Publication
 
Ashok Pandey
Research Officer, NHRC
1
The Results Section
• The core of the paper
• Often includes tables, figures, or both
• Should summarize findings rather than providing data in great
detail
• Should present results but not comment on them
• Data presentation should not repeat the data in the visuals, but
rather highlight the most important points.
• In the “standard” research paper approach, your Results section
should exclude data interpretation, leaving it for the
Discussion section
2
Results
Report the key findings,
– What you found
– not why you found it and what it means to have such findings
•Clear and concise summary of the data that was
collected and the results of any statistical tests.
•This section answers the question - What happened?
•The results section is one of the most feared sections of
the report.
– But the fear is not justified
3
4
Results
Clear and simple description of the findings
- Text should compliment tables & figures
- Highlight important findings, not details required.
Provide meaningful information - Avoid raw data!
Use of adjectives
- OK to describe quantitative differences, e.g., higher,
larger
- Avoid subjective terms, e.g., remarkable,
outstanding, interesting, significant
Mentioning tables and figures
• In citing tables and figures, emphasize the
finding, not the table or figure.
– Not so good: Table 3 shows that researchers who
attended the workshop published twice as many
papers per year.
Table 3 clearly shows that …
It is obvious from figure 4 that …
– Better: Researchers who attended the workshop
published twice as many papers per year (Table 3).
5
6
State the result and then present the data or cite a figure or
table.
In the 20 control subjects, the mean resting blood pressure was
85 ± 5(SD) mmHg. In comparison, in the 30 patients, the mean
resting blood pressure was 94 ± 3(SD) mmHg.
vs.
The mean resting blood pressure was 10% higher in the 30
patients than in the 20 control subjects (94 ± 3 [SD] vs 85
±5[SD] mmHg, P< 0.02).
Do not provide incomplete information
“People taking ibuprofen daily were more likely to have
asthma.”
More likely than whom?
Verb Tense for the Results Section:
Past Tense
Examples:
– A total of 417 samples contained . . .
– _____ increased, but _____ decreased.
– The average temperature was _____.
– Three of the dogs died.
– This difference was not statistically significant.
7
Common problems
Endless Description
• Without interpretation is another pitfall. Tables need
conclusion, not the detailed presentation of all the
number or percentages in cell
• Readers can also read tables
Sometimes qualitative data are just coded and counted like
quantitative data without interpretation even when they are
providing important information. Its serious maltreatment of
data
Example: JNHRC
Present your results in logical sequence in the text, tables, and illustrations,
giving the main or most important findings first. Do not repeat all the data in
the tables or illustrations in the text; emphasize or summarize only the most
important observations. Extra or supplementary materials and technical detail
can be placed in an appendix where they will be accessible but will not
interrupt the flow of the text, or they can be published solely in the electronic
version of the journal.
When data are summarized in the Results section, give numeric results not
only as derivatives (for example, percentages) but also as the absolute
numbers from which the derivatives were calculated, and specify the statistical
methods used to analyze them. Restrict tables and figures to those needed to
explain the argument of the paper and to assess supporting data. Use graphs as
an alternative to tables with many entries; do not duplicate data in graphs and
tables. Avoid nontechnical uses of technical terms in statistics, such as
“random” (which implies a randomizing device), “normal,” “significant,”
“correlations,” and “sample.”
Where scientifically appropriate, analyses of the data by such variables as age
and sex should be included. 10http://jnhrc.com.np/files/about.submission/author_guideline.pdf
Example: JPAHS
Present your results in logical sequence in the text, tables, and illustrations, giving the
main or most important findings first.
Do not repeat all the data in the tables or illustrations in the text; emphasize or
summarize only the most important observations.
Extra or supplementary materials and technical detail can be placed in an appendix
where they will be accessible but will not interrupt the flow of the text, or they can be
published solely in the electronic version of the journal.
When data are summarized in the Results section, give numeric results not only as
derivatives (for example, percentages) but also as the absolute numbers from which the
derivatives were calculated, and specify the statistical methods used to analyze them.
Restrict tables and figures to those needed to explain the argument of the paper and to
assess supporting data. Use graphs as an alternative to tables with many entries; do not
duplicate data in graphs and tables.
Avoid nontechnical uses of technical terms in statistics, such as “random” (which
implies a randomizing device), “normal,” “significant,” “correlations,” and “sample.”
Where scientifically appropriate, analyses of the data by such variables as age and sex
should be included.
11
Author Guidelines Journal of Patan Academy of Health Sciences
Guidelines
Lancet, Global health
JNHRC
JPAHS
12
Principles of preparing figures and
tables
Present data appropriately
Data Looks Better Naked
Use of charts and Tables
Use tables
• You need to compare
or look up individual
values.
• You require precise
values.
• The data has to
communicate
quantitative
information, but not
trends.
Use charts
• Is used to convey a
message that is
contained in the shape
of the data.
• Is used to show a
relationship between
many values
What do you want to do?
1 DV, 1IV 1 DV, >1IV
Comparison of 2 groups
Unpaired GroupUnpaired Group
Paired Group
Ratio/interval OrdinalOrdinal NominalNominal
NormalNormal
Non-
Normal
Non-
Normal
Independent
t test
Man Whitney
Test
Fisher Exact
Chi Square
Ratio/interval OrdinalOrdinal NominalNominal
NormalNormal Non-
Normal
Non-
Normal
Paired t
test
Wilcoxon Test
McNemars
Test
Kolmogorov-
Smirnov Test
Shapiro-Wilk
Test
Kolmogorov-
Smirnov Test
Shapiro-Wilk Test
One Dependent,
One Independent
Variable
Yates
Correction
Chi Square
Sample size>40, Exp cell value>5
Yates Correction
Sample size>40, Exp. cell value<5
Fisher Exact test
Sample size20-40, Exp. cell value<5
Comparison of >2 groups
Unpaired GroupUnpaired Group
Paired Group
Ratio/interval OrdinalOrdinal NominalNominal
NormalNormal
Non-
Normal
Non-
Normal
One Way
ANOVA
Kruskal Wallis
test
Chi
Square
Ratio/interval OrdinalOrdinal NominalNominal
NormalNormal
Non-
Normal
Non-
Normal
Repeated
ANOVA
Friedman Test
Cochrane
Q
TestKolmogorov-
Smirnov Test
Shapiro-Wilk
Test
Kolmogorov-
Smirnov Test
Shapiro-Wilk
Test
Logistic
Regressio
n
One Dependent,
One Independent
Variable
Other Normality tests:
Lilliefors corrected K-S test Anderson-Darling test Cramer-von Mises test Jarque-Bera test
Tables and Figures
• Foundation of your paper – tells the story
• Minimum no. of tables and figures (journals have limits)
• Do not present same data in tables and figures
• Know when to use a table vs. a figure
• Use similar formats so readers do not have to reorient
themselves to each table / figure
• Make them look professional – use footnotes
• Make sure all are cited in the text
• Do not waste space - Make use of Supplemental Material
20
Basic rules for the preparation of tables and
graphs
Ideally, every table should:
• Be self-explanatory;
• Present values with the same number of decimal places in all its
cells
• Include a title informing what is being described and where, as
well as the number of observations
• Have a structure formed by three horizontal lines, defining table
heading and the end of the table at its lower border;
• Not have vertical lines
• Provide additional information in table footer, when needed
• Be inserted into a document only after being mentioned in the
text; and
• Be numbered by Arabic numerals.
22
Frugal use of "non-data ink"
Pie Chart
• https://speakerdeck.com/
cherdarchuk/data-looks-
better-naked-pie-chart-
edition
Bar Diagram
• https://speakerdeck.com/
cherdarchuk/remove-to-
improve-the-data-ink-ratio
24
Results: A Suggestion
• Look at the Results sections of some papers in
your target journal.
• Notice items such as the following:
– Length
– Organization
– Inclusion of subheads (or not)
– Number of tables and figures
• Use these Results sections as models.
25
Thank you!
26

Writing the results section for scientific publication

  • 1.
    Results section (Principlesof preparing figures and tables) Training Workshop on Scientific Research, Communication and Publication   Ashok Pandey Research Officer, NHRC 1
  • 2.
    The Results Section •The core of the paper • Often includes tables, figures, or both • Should summarize findings rather than providing data in great detail • Should present results but not comment on them • Data presentation should not repeat the data in the visuals, but rather highlight the most important points. • In the “standard” research paper approach, your Results section should exclude data interpretation, leaving it for the Discussion section 2
  • 3.
    Results Report the keyfindings, – What you found – not why you found it and what it means to have such findings •Clear and concise summary of the data that was collected and the results of any statistical tests. •This section answers the question - What happened? •The results section is one of the most feared sections of the report. – But the fear is not justified 3
  • 4.
    4 Results Clear and simpledescription of the findings - Text should compliment tables & figures - Highlight important findings, not details required. Provide meaningful information - Avoid raw data! Use of adjectives - OK to describe quantitative differences, e.g., higher, larger - Avoid subjective terms, e.g., remarkable, outstanding, interesting, significant
  • 5.
    Mentioning tables andfigures • In citing tables and figures, emphasize the finding, not the table or figure. – Not so good: Table 3 shows that researchers who attended the workshop published twice as many papers per year. Table 3 clearly shows that … It is obvious from figure 4 that … – Better: Researchers who attended the workshop published twice as many papers per year (Table 3). 5
  • 6.
    6 State the resultand then present the data or cite a figure or table. In the 20 control subjects, the mean resting blood pressure was 85 ± 5(SD) mmHg. In comparison, in the 30 patients, the mean resting blood pressure was 94 ± 3(SD) mmHg. vs. The mean resting blood pressure was 10% higher in the 30 patients than in the 20 control subjects (94 ± 3 [SD] vs 85 ±5[SD] mmHg, P< 0.02). Do not provide incomplete information “People taking ibuprofen daily were more likely to have asthma.” More likely than whom?
  • 7.
    Verb Tense forthe Results Section: Past Tense Examples: – A total of 417 samples contained . . . – _____ increased, but _____ decreased. – The average temperature was _____. – Three of the dogs died. – This difference was not statistically significant. 7
  • 8.
    Common problems Endless Description •Without interpretation is another pitfall. Tables need conclusion, not the detailed presentation of all the number or percentages in cell • Readers can also read tables Sometimes qualitative data are just coded and counted like quantitative data without interpretation even when they are providing important information. Its serious maltreatment of data
  • 9.
    Example: JNHRC Present yourresults in logical sequence in the text, tables, and illustrations, giving the main or most important findings first. Do not repeat all the data in the tables or illustrations in the text; emphasize or summarize only the most important observations. Extra or supplementary materials and technical detail can be placed in an appendix where they will be accessible but will not interrupt the flow of the text, or they can be published solely in the electronic version of the journal. When data are summarized in the Results section, give numeric results not only as derivatives (for example, percentages) but also as the absolute numbers from which the derivatives were calculated, and specify the statistical methods used to analyze them. Restrict tables and figures to those needed to explain the argument of the paper and to assess supporting data. Use graphs as an alternative to tables with many entries; do not duplicate data in graphs and tables. Avoid nontechnical uses of technical terms in statistics, such as “random” (which implies a randomizing device), “normal,” “significant,” “correlations,” and “sample.” Where scientifically appropriate, analyses of the data by such variables as age and sex should be included. 10http://jnhrc.com.np/files/about.submission/author_guideline.pdf
  • 10.
    Example: JPAHS Present yourresults in logical sequence in the text, tables, and illustrations, giving the main or most important findings first. Do not repeat all the data in the tables or illustrations in the text; emphasize or summarize only the most important observations. Extra or supplementary materials and technical detail can be placed in an appendix where they will be accessible but will not interrupt the flow of the text, or they can be published solely in the electronic version of the journal. When data are summarized in the Results section, give numeric results not only as derivatives (for example, percentages) but also as the absolute numbers from which the derivatives were calculated, and specify the statistical methods used to analyze them. Restrict tables and figures to those needed to explain the argument of the paper and to assess supporting data. Use graphs as an alternative to tables with many entries; do not duplicate data in graphs and tables. Avoid nontechnical uses of technical terms in statistics, such as “random” (which implies a randomizing device), “normal,” “significant,” “correlations,” and “sample.” Where scientifically appropriate, analyses of the data by such variables as age and sex should be included. 11 Author Guidelines Journal of Patan Academy of Health Sciences
  • 11.
  • 12.
    Principles of preparingfigures and tables Present data appropriately Data Looks Better Naked
  • 13.
    Use of chartsand Tables Use tables • You need to compare or look up individual values. • You require precise values. • The data has to communicate quantitative information, but not trends. Use charts • Is used to convey a message that is contained in the shape of the data. • Is used to show a relationship between many values
  • 16.
    What do youwant to do? 1 DV, 1IV 1 DV, >1IV
  • 17.
    Comparison of 2groups Unpaired GroupUnpaired Group Paired Group Ratio/interval OrdinalOrdinal NominalNominal NormalNormal Non- Normal Non- Normal Independent t test Man Whitney Test Fisher Exact Chi Square Ratio/interval OrdinalOrdinal NominalNominal NormalNormal Non- Normal Non- Normal Paired t test Wilcoxon Test McNemars Test Kolmogorov- Smirnov Test Shapiro-Wilk Test Kolmogorov- Smirnov Test Shapiro-Wilk Test One Dependent, One Independent Variable Yates Correction Chi Square Sample size>40, Exp cell value>5 Yates Correction Sample size>40, Exp. cell value<5 Fisher Exact test Sample size20-40, Exp. cell value<5
  • 18.
    Comparison of >2groups Unpaired GroupUnpaired Group Paired Group Ratio/interval OrdinalOrdinal NominalNominal NormalNormal Non- Normal Non- Normal One Way ANOVA Kruskal Wallis test Chi Square Ratio/interval OrdinalOrdinal NominalNominal NormalNormal Non- Normal Non- Normal Repeated ANOVA Friedman Test Cochrane Q TestKolmogorov- Smirnov Test Shapiro-Wilk Test Kolmogorov- Smirnov Test Shapiro-Wilk Test Logistic Regressio n One Dependent, One Independent Variable Other Normality tests: Lilliefors corrected K-S test Anderson-Darling test Cramer-von Mises test Jarque-Bera test
  • 19.
    Tables and Figures •Foundation of your paper – tells the story • Minimum no. of tables and figures (journals have limits) • Do not present same data in tables and figures • Know when to use a table vs. a figure • Use similar formats so readers do not have to reorient themselves to each table / figure • Make them look professional – use footnotes • Make sure all are cited in the text • Do not waste space - Make use of Supplemental Material 20
  • 20.
    Basic rules forthe preparation of tables and graphs Ideally, every table should: • Be self-explanatory; • Present values with the same number of decimal places in all its cells • Include a title informing what is being described and where, as well as the number of observations • Have a structure formed by three horizontal lines, defining table heading and the end of the table at its lower border; • Not have vertical lines • Provide additional information in table footer, when needed • Be inserted into a document only after being mentioned in the text; and • Be numbered by Arabic numerals.
  • 21.
  • 22.
    Frugal use of"non-data ink" Pie Chart • https://speakerdeck.com/ cherdarchuk/data-looks- better-naked-pie-chart- edition Bar Diagram • https://speakerdeck.com/ cherdarchuk/remove-to- improve-the-data-ink-ratio
  • 23.
  • 24.
    Results: A Suggestion •Look at the Results sections of some papers in your target journal. • Notice items such as the following: – Length – Organization – Inclusion of subheads (or not) – Number of tables and figures • Use these Results sections as models. 25
  • 25.

Editor's Notes

  • #19 Sapiro wilk test better when sample size less than 2000